Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to rankings and standings in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atee
    -0.18
    ucle
    -0.16
     Eb
    -0.14
     Walters
    -0.14
    á»ĵn
    -0.14
    ession
    -0.14
     Roz
    -0.13
     Norm
    -0.13
    kins
    -0.13
    ť
    -0.13
    POSITIVE LOGITS
    irie
    0.14
     reflect
    0.14
     polls
    0.14
    Sha
    0.14
    apat
    0.14
    orc
    0.14
    è³ĩ
    0.14
    ourke
    0.14
    coc
    0.14
    xFE
    0.14
    Act Density 0.013%

    No Known Activations